12 papers
On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
Sunghwan Kim, Junhee Cho, Beong-woo Kwak +6
Large language models (LLMs) have shown promise as interactive agents that solve tasks through extended sequences of environment interactions. While prior work has primarily focuse…
Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
Wen Luo, Guangyue Peng, Wei Li +8
Despite their impressive capabilities, large language models (LLMs) frequently generate hallucinations. Previous work shows that their internal states encode rich signals of truthf…
RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning
Shaopeng Fu, Xingxing Zhang, Li Dong +2
While large language models (LLMs) have demonstrated strong performance on complex reasoning tasks such as competitive programming (CP), existing methods predominantly focus on sin…
Learning to Draft: Adaptive Speculative Decoding with Reinforcement Learning
Jiebin Zhang, Zhenghan Yu, Liang Wang +8
Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of…
QueST: Incentivizing LLMs to Generate Difficult Problems
Hanxu Hu, Xingxing Zhang, Jannis Vamvas +2
Large Language Models have achieved strong performance on reasoning tasks, solving competition-level coding and math problems. However, their scalability is limited by human-labele…
Scaling Laws of Synthetic Data for Language Models
Zeyu Qin, Qingxiu Dong, Xingxing Zhang +10
Large language models (LLMs) achieve strong performance across diverse tasks, largely driven by high-quality web data used in pre-training. However, recent studies indicate this da…